MODELING OF MEMBRANE INFLATION IN BLOW MOLDING - NEURAL-NETWORK PREDICTION OF INITIAL DIMENSIONS FROM FINAL PART SPECIFICATIONS

The use of neural networks in the modeling of the inflation stage of t he blow molding process is discussed. The simulation is enacted in the reverse process direction, predicting initial membrane dimension requ irements from final part thickness distributions. This situation has p ractical implications because tooling costs and machine downtimes can be minimized with the information obtained. The optimal network topolo gy entails simultaneous pre- and postprocessing of the data. An adapti ve window is employed for modeling of the effects of adjacent segments . The optimal window length is 16 for both the input and output layers in the network topology. Simulations are run for bottles blown using various constant and pulsed die gaps.